Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

Naseer, Muhammad Muzammal; Khan, Salman; Porikli, Fatih

doi:10.1109/access.2018.2886133

Cited by 88 publications

(57 citation statements)

References 209 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of low cost 3D sensors, researchers are focusing on deep learning methods for 3D object recognition. Following the classification presented in [7], we divide the methods in terms of the most used data representation.…”

Section: Related Workmentioning

confidence: 99%

Par3DNet: Using 3DCNNs for Object Recognition on Tridimensional Partial Views

Gomez-Donoso

Cazorla

2020

Applied Sciences

View full text Add to dashboard Cite

Deep learning-based methods have proven to be the best performers when it comes to object recognition cues both in images and tridimensional data. Nonetheless, when it comes to 3D object recognition, the authors tend to convert the 3D data to images and then perform their classification. However, despite its accuracy, this approach has some issues. In this work, we present a deep learning pipeline for object recognition that takes a point cloud as input and provides the classification probabilities as output. Our proposal is trained on synthetic CAD objects and is able to perform accurately when fed with real data provided by commercial sensors. Unlike most approaches, our method is specifically trained to work on partial views of the objects rather than on a full representation, which is not the representation of the objects as captured by commercial sensors. We trained our proposal with the ModelNet10 dataset and achieved a 78.39 % accuracy. We also tested it by adding noise to the dataset and against a number of datasets and real data with high success.

show abstract

Section: Related Workmentioning

confidence: 99%

Par3DNet: Using 3DCNNs for Object Recognition on Tridimensional Partial Views

Gomez-Donoso

Cazorla

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Indoor datasets. Naseer et al [38] gave a comprehensive overview of indoor scene understanding in 2.5/3D. The first dataset is NYU-Depth with two versions introduced by Silberman et al [39] using Microsoft Kinect.…”

Section: Related Workmentioning

confidence: 99%

Learning to Reconstruct and Understand Indoor Scenes From Sparse Views

Yang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3-5) color images from uncalibrated sparse views as input, which greatly simplifies data acquisition and extends applicable scenarios. Since different views have limited overlaps, our method allows a single image as input to discern the depth and semantic information of the scene. The key issue is how to recover relatively accurate depth from single images and reconstruct a 3D scene by fusing very few depth maps. To address this problem, we first design an iterative deep architecture, Iter-Net, that estimates depth and semantic segmentation alternately, so that they benefit each other. To deal with the little overlap and non-rigid transformation between views, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information from sparse views. We also make available a new indoor synthetic dataset simultaneously providing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts, useful for training and evaluation. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors and better 3D reconstruction results, compared with stateof-the-art methods.

show abstract

“…Primitive Discovery: Cuboids have been extensively used in the previous literature to represent objects, parts and scene structural elements due to their simple form [32,18,15,23]. The identification of recurring parts and objects has also been studied under the problems of cosegmentation and unsupervised learning [28,34,29].…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Primitive Discovery for Improved 3D Generative Modeling

Khan

Guo

Hayat

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D shapes. Here, we propose a novel factorized generative model for 3D shape generation that sequentially transitions from coarse to fine scale shape generation. To this end, we introduce an unsupervised primitive discovery algorithm based on a higher-order conditional random field model. Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage. This representation is further refined in the next stage by adding fine scale details to shape. Our results demonstrate improved representation ability of the generative model and better quality samples of newly generated 3D shapes. Further, our primitive generation approach can accurately parse common objects into a simplified representation.

show abstract

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

Cited by 88 publications

References 209 publications

Par3DNet: Using 3DCNNs for Object Recognition on Tridimensional Partial Views

Par3DNet: Using 3DCNNs for Object Recognition on Tridimensional Partial Views

Learning to Reconstruct and Understand Indoor Scenes From Sparse Views

Unsupervised Primitive Discovery for Improved 3D Generative Modeling

Contact Info

Product

Resources

About